© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60770
    Prev
    Next
    INDEX
    Explanations

    gender presentation and identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    равда
    -0.80
     bunt
    -0.77
     warmed
    -0.77
    msubsup
    -0.76
    ｐ
    -0.75
    Im
    -0.71
    olver
    -0.71
    ｓ
    -0.70
     Neri
    -0.70
    unite
    -0.70
    POSITIVE LOGITS
     femme
    1.41
    coded
    1.41
     coded
    1.38
     masculine
    1.33
     femin
    1.33
     assigned
    1.29
     feminine
    1.27
     femininity
    1.25
     presentation
    1.24
    presentation
    1.22
    Activations Density 0.044%

    No Known Activations